CN112506635B - Evolutionary immunization method based on self-adaptive strategy - Google Patents
Evolutionary immunization method based on self-adaptive strategy Download PDFInfo
- Publication number
- CN112506635B CN112506635B CN202011461165.0A CN202011461165A CN112506635B CN 112506635 B CN112506635 B CN 112506635B CN 202011461165 A CN202011461165 A CN 202011461165A CN 112506635 B CN112506635 B CN 112506635B
- Authority
- CN
- China
- Prior art keywords
- population
- offspring
- evolution operator
- differential evolution
- adaptive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000003053 immunization Effects 0.000 title claims abstract description 15
- 238000002649 immunization Methods 0.000 title claims abstract description 15
- 230000006872 improvement Effects 0.000 claims abstract description 26
- 230000003044 adaptive effect Effects 0.000 claims abstract description 20
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 238000011156 evaluation Methods 0.000 claims abstract description 8
- 238000012163 sequencing technique Methods 0.000 claims abstract description 4
- 230000006978 adaptation Effects 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000005265 energy consumption Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 7
- 238000010367 cloning Methods 0.000 claims description 4
- 230000035772 mutation Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000003595 mist Substances 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Feedback Control In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an evolutionary immunization method based on a self-adaptive strategy, which comprises the following steps: s1, initializing parameters and constructing a differential evolution operator pool; s2, randomly selecting a differential evolution operator to generate immune individuals in the population; s3, dividing the population into a plurality of sub-populations with the same size, calculating each target value of immune individuals, and sequencing and reserving elite solutions under each target value; s4, selecting a clone offspring of a differential evolution operator according to the adaptive value improvement rate of offspring and father in each sub population; s5, based on a non-dominant sorting strategy, obtaining non-dominant solutions in all sub-populations, and constructing an elite solution set; and S6, updating the individual evaluation times, executing the step S4 until the individual evaluation times reach a time threshold value, and outputting an optimal solution. And storing each evolution operator by utilizing a sliding window to generate an adaptive value of the population individuals, evaluating the advantages and disadvantages of each evolution operator, and selecting the optimal evolution operator in a self-adaptive mode to execute population optimization.
Description
Technical Field
The invention relates to the technical field of fog calculation, and provides an evolutionary immunization method based on a self-adaptive strategy.
Background
At present, fog calculation is widely focused by researchers at home and abroad. The fog calculation consists of scattered terminal equipment, an edge server, network interconnection equipment and the like, and can provide services such as calculation unloading, storage resources and the like. The fog calculation can be regarded as network extension of cloud calculation, and has the characteristics of low time delay, real-time interaction, position sensing, mobile support and the like. Because the fog calculation server is close to the mobile terminal, the transmission time delay required by the mobile terminal to transmit the task to the fog calculation is small, so that the mobile terminal unloads the application with complex calculation and higher time delay requirement into the fog calculation, and simultaneously, the transmission energy consumption of the mobile terminal and the link bandwidth transmitted to the cloud are also saved. However, fog servers have lower computing power than cloud servers. The problem of fog computing resource management and scheduling is a key to influence the performance of fog computing services, and particularly when large-scale service requests occur, if the problem of resource scheduling cannot be effectively solved, the problems of service delay, resource utilization rate reduction, user satisfaction and the like are increased. In fog computing resource management and scheduling, multiple objectives such as task time delay, energy consumption, billing and the like need to be considered simultaneously. How to optimize these objective functions simultaneously becomes a current difficulty in fog computing resource management and scheduling.
In recent years, immune algorithms have become one of the mainstream algorithms for solving the multi-objective optimization problem. However, conventional immune algorithms perform population evolution processes using only a single evolution operator, which can lead to difficult handling of complex multi-objective optimization problems. Even if different evolutionary operators are used for combination, a plurality of parameters are required to be adjusted, and population convergence and diversity are difficult to balance.
Disclosure of Invention
The invention provides an evolutionary immunization method based on an adaptive strategy, which aims to improve the problems.
The invention is realized in such a way that an evolutionary immunization method based on an adaptive strategy comprises the following steps:
s1, initializing parameters and constructing a differential evolution operator pool;
s2, initializing a population: randomly selecting a differential evolution operator from a differential evolution operator pool to generate immune individuals in the population, wherein one immune individual corresponds to a resource scheduling scheme of fog calculation;
s3, dividing the population into a plurality of sub-populations with the same size, calculating each target value of immune individuals, and sequencing and reserving elite solutions under each target value;
s4, selecting a clone offspring of a differential evolution operator according to the adaptive value improvement rate of offspring and father in each sub population;
s5, based on a non-dominant sorting strategy, obtaining non-dominant solutions in all sub-populations, and constructing an elite solution set;
and S6, updating the individual evaluation times, executing the step S4 until the individual evaluation times reach a time threshold value, and outputting an optimal solution.
Further, the target value is calculated based on an objective function consisting of a time delay objective function for completion of the task, an energy consumption objective function for execution of the task by the fog node, and a cost objective function generated when the fog node executes the task.
Further, the step S4 specifically includes the following steps:
s41, defining a sliding window, wherein the sliding window is used for storing a two-dimensional array structure of an adaptation value improvement rate between a offspring and a father and a corresponding differential evolution operator index;
s42, putting the adaptation value improvement rate between each offspring and the father in the child population and the selected differential evolution operator index into the sliding window until the sliding window is full;
s43, selecting a differential evolution operator corresponding to the maximum adaptation value improvement rate in the sliding window to execute cloning of offspring individuals on the sub population.
Further, the calculation formula of the adaptive value improvement rate FIR is specifically as follows:
wherein pf is i Representing the ith target value, cf, of the offspring individual i Representing the ith target value of the parent individual.
Further, after the adaptation value improvement rate of the offspring and the father and the selected differential evolution operator in the child population are placed in the sliding window, if the sliding window is not full, elite solution and the randomly selected differential evolution operator are randomly selected to generate offspring individuals, and the adaptation value improvement rate between the offspring and the father and the selected differential evolution operator are placed in the sliding window until the sliding window is filled.
Further, the delay objective function is specifically as follows:wherein RT i,j For the theoretical runtime of the current task i on the virtual resource j, TC i,j =1 means that the current task i runs on virtual resource j, whereas TC i,j ＝0；
The energy consumption objective function is expressed as follows:wherein EC is ij The energy which is needed to be consumed by the task j in the virtual resource i is represented;
the cost objective function is specifically as follows: o (O) 3 ＝RT i,j * perDJ; wherein RT i,j Representing the run time of the computing task i in the virtual resource j, perDJ represents the computational unit price of the cloud node resource.
Further, the differential evolution operator pool is composed of at least 2 differential evolution operators.
The invention designs a novel evolutionary immunization method based on an adaptive strategy, which is used for optimizing the problems of fog computing resource management and scheduling. In the method, a plurality of differential evolution operators form a differential evolution operator pool. In the population optimization process, each evolution operator is saved by utilizing a sliding window to generate an adaptation value of a population individual, the merits of each evolution operator are evaluated, and the optimal evolution operator is selected in a self-adaptive mode to execute the population optimization process. The invention improves the immune algorithm, fuses different differential evolution operators, and is used for solving the problems of multi-target fog computing resource management and scheduling.
Drawings
FIG. 1 is a schematic diagram of a fog computing resource scheduling scheme provided by an embodiment of the present invention;
fig. 2 is a flowchart of an evolutionary immunization method based on an adaptive strategy according to an embodiment of the present invention.
Detailed Description
The following detailed description of the invention refers to the accompanying drawings, which illustrate preferred embodiments of the invention in further detail.
Step 1. Parameter initialization and Gene representation
Firstly, initializing parameters such as the number of mist computing nodes, storage capacity, energy consumption and the like; then, initializing the task quantity and the data quantity of the request processing; initializing population scale and gene coding representation of population individuals according to the number of tasks and the number of mist calculation nodes as shown in figure 1; wherein t is i Representing the number of calculation tasks, i.e. [1, m ]]，r j Represents the resource number, j E [1, n ]]. The corresponding decoding r can be obtained according to the coding mode 3 :{t 1 }，r 1 :{t 2 }，r 2 :{t 3 }，…，r n :{t m It can be seen that each individual corresponds to an implementation of fog computing resource scheduling.
Step 2, constructing a differential evolution operator pool
1) DE/rand/1 "mutation strategy: is the most common mutation strategy, where all the difference vectors are randomly selected from the evolving population. Thus, it has no bias on any particular search direction, choosing a new search direction randomly at a time.
2) DE/rand/2 "mutation strategy: with two differential vectors, it is possible to have a larger amount of disturbance information than "DE/rand/1".
3) DE/current-to-rand/1 mutation strategy: the current solution is added to the two differential vectors to accelerate convergence.
Step 3. Fog calculation objective function
(1) Time delay: each specific task completion time is from task submission to feedback of task computing completion to the user. In the study, the time delay is defined as the time used by the task with the longest completion time in all tasks, and the calculation formula of the time delay objective function is specifically as follows:
wherein RT i,j For the theoretical runtime of the current task i on the virtual resource j, TC i,j =1 means that the current task i runs on virtual resource j, whereas TC i,j ＝0。
(2) Energy consumption: the second objective function is defined as the energy consumption of each fog computing node executing the computing task, and the computing formula of the energy consumption objective function is specifically as follows:
wherein EC is ij The virtual resource i represents the energy consumed by the task j in running.
(3) Charging: the third objective function is defined as the cost generated when each fog computing node executes the computing task, and the computing formula of the cost objective function is specifically as follows:
O 3 ＝RT i,j *perDJ
wherein RT i,j Representing the run time of the computing task i in the virtual resource j, perDJ represents the computational unit price of the cloud node resource.
Fig. 2 is a flowchart of an adaptive strategy-based evolutionary immunization method according to an embodiment of the present invention, which specifically includes the following steps:
s1, initializing parameters and constructing a differential evolution operator pool;
s2, initializing a population: randomly selecting a differential evolution operator from a differential evolution operator pool, generating immune individuals in the population, and repeatedly executing until the number of the immune individuals in the population reaches a specified number;
s3, dividing the population into a plurality of sub-populations with the same size, and calculating target values of each immune individual, including a delay target, an energy consumption target and a cost target value, and sequencing and reserving elite sets under the target values.
And S4, selecting a differential evolution operator to generate offspring based on the adaptive value improvement rate for each sub population.
In the embodiment of the present invention, the step S4 specifically includes the following steps:
s41, defining a sliding window, wherein the sliding window is defined as a two-dimensional array structure and is used for storing the adaptation value improvement rate between the offspring and the father and the index of the current differential evolution operator.
In the embodiment of the invention, the adaptive value improvement rate FIR calculation formulas of offspring and father are specifically as follows:
wherein pf is i Representing the ith target value, cf, of the offspring individual i Representing the ith target value of the parent individual.
S42, putting the adaptation value improvement rate between each offspring and the father in the child population and the selected differential evolution operator index into the sliding window until the sliding window is full; if the sliding window is not full, generating offspring individuals by randomly selecting elite solution and randomly selected differential evolution operators, calculating the adaptation value improvement rate of offspring and father, and storing the adaptation value improvement rate and the selected differential evolution operator index into the sliding window until the sliding window is full.
Assuming that the number of groups defining the sliding window is 5, 5 individuals exist in the sub-population, randomly selecting differential evolution operators in a differential evolution operator pool by the 5 individuals respectively, assuming that different differential evolution operators in the 5 are selected as a final selection result, respectively calculating the adaptation value improvement rates of offspring and father corresponding to the 5 differential evolution operators, and then selecting the differential evolution operator corresponding to the maximum adaptation value improvement rate to clone the sub-population next time.
S43, selecting a differential evolution operator corresponding to the maximum adaptation value improvement rate in the sliding window to execute cloning of offspring individuals on the sub population where the differential evolution operator is located. When only one differential evolution operator exists in the sliding window, randomly selecting one differential evolution operator to execute cloning of offspring individuals. Each sub-population employs the same execution.
S5, based on a non-dominant sorting strategy, obtaining non-dominant solutions in all sub-populations and constructing an elite solution set:
and S6, updating the individual evaluation times, executing the step S4 until the individual evaluation times reach a time threshold value, and outputting an optimal solution.
The invention designs a novel evolutionary immunization method based on an adaptive strategy, which is used for optimizing the problems of fog computing resource management and scheduling. In the method, a plurality of differential evolution operators form a differential evolution operator pool. In the population optimization process, each evolution operator is saved by utilizing a sliding window to generate an adaptation value of a population individual, the merits of each evolution operator are evaluated, and the optimal evolution operator is selected in a self-adaptive mode to execute the population optimization process. The invention improves the immune algorithm, fuses different differential evolution operators, and is used for solving the problems of multi-target fog computing resource management and scheduling.
It is obvious that the specific implementation of the present invention is not limited by the above-mentioned modes, and that it is within the scope of protection of the present invention only to adopt various insubstantial modifications made by the method conception and technical scheme of the present invention.
Claims (5)
1. An evolutionary immunization method based on an adaptive strategy, which is characterized by comprising the following steps:
s1, initializing parameters and constructing a differential evolution operator pool;
s2, initializing a population: randomly selecting a differential evolution operator from the differential evolution operator pool to generate immune individuals in the population, wherein one immune individual corresponds to a resource scheduling scheme of fog calculation;
s3, dividing the population into a plurality of sub-populations with the same size, calculating each target value of immune individuals, and sequencing and reserving elite solutions under each target value;
s4, selecting a clone offspring of a differential evolution operator according to the adaptive value improvement rate of offspring and father in each sub population;
s5, based on a non-dominant sorting strategy, obtaining non-dominant solutions in all sub-populations, and constructing an elite solution set;
s6, updating the individual evaluation times, executing the step S4 until the individual evaluation times reach a time threshold value, and outputting an optimal solution;
the target value is calculated based on an objective function, wherein the objective function consists of a time delay objective function for completing a task, an energy consumption objective function for executing the task by a fog node and a cost objective function generated when the fog node executes the task;
the delay objective function is specifically as follows:wherein RT i,j For the theoretical runtime of the current task i on the virtual resource j, TC i,j =1 means that the current task i runs on virtual resource j, whereas TC i,j ＝0；
The energy consumption objective function is expressed as follows:wherein EC is ij The energy which is needed to be consumed by the task j in the virtual resource i is represented;
the cost objective function is specifically as follows: o (O) 3 ＝RT i,j * perDJ; wherein RT i,j Representing the running time of the computing task i in the virtual resource j, and perDJ represents the computing unit price of the fog node resource;
when the offspring is cloned based on the self-adaptive value improvement rate of the offspring and the father in the sub-population, the self-adaptive value improvement rate of the offspring and the father in the sub-population is used for storing each evolution operator to generate the adaptive value of the population individual through a sliding window in the population optimization process, the quality of each evolution operator is evaluated, and the optimal evolution operator is selected in a self-adaptive mode to execute the population optimization process.
2. The adaptive strategy-based evolutionary immunization method as claimed in claim 1, wherein said step S4 comprises the steps of:
s41, defining a sliding window, wherein the sliding window is used for storing a two-dimensional array structure of an adaptation value improvement rate between a offspring and a father and a corresponding differential evolution operator index;
s42, putting the adaptation value improvement rate between each offspring and the father in the child population and the selected differential evolution operator index into the sliding window until the sliding window is full;
s43, selecting a differential evolution operator corresponding to the maximum adaptation value improvement rate in the sliding window to execute cloning of offspring individuals on the sub population.
3. The adaptive strategy-based evolutionary immunization method as claimed in claim 2, wherein the adaptive value improvement rate FIR is calculated as follows:
wherein pf is i Representing the ith target value, cf, of the offspring individual i Representing the ith target value of the parent individual.
4. The adaptive strategy-based evolutionary immunization method as claimed in claim 2, wherein after the adaptation value improvement rate of the offspring and the father in the sub-population and the selected differential evolution operator are placed in the sliding window, if the sliding window is not full, elite solution and the randomly selected differential evolution operator are randomly selected to generate offspring individuals, and the adaptation value improvement rate between the offspring and the father and the selected differential evolution operator are placed in the sliding window until the sliding window is filled.
5. The adaptive strategy-based evolutionary immunization method of claim 1, wherein the pool of differential evolution operators consists of at least 2 differential evolution operators.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011461165.0A CN112506635B (en) | 2020-12-11 | 2020-12-11 | Evolutionary immunization method based on self-adaptive strategy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011461165.0A CN112506635B (en) | 2020-12-11 | 2020-12-11 | Evolutionary immunization method based on self-adaptive strategy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112506635A CN112506635A (en) | 2021-03-16 |
| CN112506635B true CN112506635B (en) | 2024-03-29 |
Family
ID=74972350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011461165.0A Active CN112506635B (en) | 2020-12-11 | 2020-12-11 | Evolutionary immunization method based on self-adaptive strategy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112506635B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596339A (en) * | 2018-03-15 | 2018-09-28 | 中山大学 | A kind of multi-objective Optimization Genetic Algorithm of structure population and subproblem |
| CN110321217A (en) * | 2019-03-25 | 2019-10-11 | 深圳大学 | A kind of cloud resource dispatching method, device, equipment and the storage medium of multiple target |
| CN111191343A (en) * | 2019-12-05 | 2020-05-22 | 西安理工大学 | Multi-mode multi-target differential evolution algorithm based on random sequencing learning |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10924534B2 (en) * | 2019-03-01 | 2021-02-16 | Akamai Technologies, Inc. | Dynamic placement of computing tasks in a distributed computing environment |
| US20200142735A1 (en) * | 2019-09-28 | 2020-05-07 | Intel Corporation | Methods and apparatus to offload and onload workloads in an edge environment |
-
2020
- 2020-12-11 CN CN202011461165.0A patent/CN112506635B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596339A (en) * | 2018-03-15 | 2018-09-28 | 中山大学 | A kind of multi-objective Optimization Genetic Algorithm of structure population and subproblem |
| CN110321217A (en) * | 2019-03-25 | 2019-10-11 | 深圳大学 | A kind of cloud resource dispatching method, device, equipment and the storage medium of multiple target |
| CN111191343A (en) * | 2019-12-05 | 2020-05-22 | 西安理工大学 | Multi-mode multi-target differential evolution algorithm based on random sequencing learning |
Non-Patent Citations (6)
| Title |
|---|
| Immune network algorithm applied to the optimization of composite SaaS in cloud computing;S. A. Ludwig and K. Bauer;2015 IEEE Congress on Evolutionary Computation (CEC);20150914;全文 * |
| 具有自学习能力的变异蝙蝠优化算法及性能仿真;尚俊娜;刘春菊;岳克强;李林;;系统仿真学报;20170208(02);全文 * |
| 函数优化问题求解的自适应差分进化算法;张延莉;;内蒙古师范大学学报(自然科学汉文版);20171115(06);全文 * |
| 基于云雾混合计算的车联网联合资源分配算法;唐伦;肖娇;魏延南;赵国繁;陈前斌;;电子与信息学报;20200815(08);全文 * |
| 多目标差分演化算法研究综述;敖友云;迟洪钦;;计算机科学与探索;20090515(03);全文 * |
| 融合区块链与雾计算系统中基于网络时延和资源管理的优化任务卸载方案;刘通;唐伦;何小强;陈前斌;;电子与信息学报;20200915(09);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112506635A (en) | 2021-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112882815B (en) | Multi-user edge calculation optimization scheduling method based on deep reinforcement learning | |
| CN107172166B (en) | Cloud and mist computing system for industrial intelligent service | |
| US20210133534A1 (en) | Cloud task scheduling method based on phagocytosis-based hybrid particle swarm optimization and genetic algorithm | |
| CN112286677B (en) | Resource-constrained edge cloud-oriented Internet of things application optimization deployment method | |
| CN109840154B (en) | Task dependency-based computing migration method in mobile cloud environment | |
| CN111866954A (en) | User selection and resource allocation method based on federal learning | |
| CN107656799B (en) | Workflow scheduling method considering communication and computing cost under multi-cloud environment | |
| CN111585816A (en) | Task unloading decision method based on adaptive genetic algorithm | |
| CN114585006B (en) | Edge computing task unloading and resource allocation method based on deep learning | |
| CN112685138A (en) | Multi-workflow scheduling method based on multi-population hybrid intelligent optimization in cloud environment | |
| ABDULKAREEM et al. | OPTIMIZATION OF LOAD BALANCING ALGORITHMS TO DEAL WITH DDOS ATTACKS USING WHALE OPTIMIZATION ALGORITHM | |
| CN110996365B (en) | Heterogeneous network vertical switching algorithm and system based on multi-objective optimization model | |
| CN116107692A (en) | Edge container multi-target ant colony optimization scheduling method for dynamic fusion genetic algorithm | |
| CN113139639B (en) | MOMBI-oriented smart city application multi-target computing migration method and device | |
| Ma et al. | NSGA-II with local search for multi-objective application deployment in multi-cloud | |
| Han et al. | Multi-step reinforcement learning-based offloading for vehicle edge computing | |
| Saemi et al. | A new optimization approach for task scheduling problem using water cycle algorithm in mobile cloud computing | |
| CN112506635B (en) | Evolutionary immunization method based on self-adaptive strategy | |
| Alexandrescu et al. | A genetic algorithm for mapping tasks in heterogeneous computing systems | |
| CN116089083A (en) | Multi-target data center resource scheduling method | |
| CN114650321A (en) | Task scheduling method for edge computing and edge computing terminal | |
| CN110233763B (en) | Virtual network embedding algorithm based on time sequence difference learning | |
| Bensalem et al. | Towards optimal serverless function scaling in edge computing network | |
| CN115016889A (en) | Virtual machine optimization scheduling method for cloud computing | |
| CN113127167A (en) | Heterogeneous resource intelligent parallel scheduling method based on improved genetic algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |